mboillet commited on
Commit
d781d58
1 Parent(s): b931bc0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -13
README.md CHANGED
@@ -21,15 +21,15 @@ pipeline_tag: image-to-text
21
 
22
  # PyLaia - POPP
23
 
24
- This model performs Handwritten Text Recognition on French census documents.
25
 
26
  ## Model description
27
 
28
  The model was trained using the PyLaia library on the [POPP generic](https://github.com/Shulk97/POPP-datasets/).
29
 
30
- For training, text-lines were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
31
 
32
- | split | N lines |
33
  | ----- | ------: |
34
  | train | 3,835 |
35
  | val | 480 |
@@ -41,22 +41,26 @@ An external 6-gram character language model can be used to improve recognition.
41
 
42
  The model achieves the following results:
43
 
44
- | set | Language model | CER (%) | WER (%) | N lines |
45
- |:------|:---------------| ----------:| -------:|----------:|
46
- | test | no | 16.49 | 36.26 | 479 |
47
- | test | yes | 16.09 | 34.52 | 479 |
48
 
49
  ## How to use?
50
 
51
- Please refer to the [documentation](https://atr.pages.teklia.com/pylaia/).
52
 
53
  ## Cite us!
54
 
55
  ```bibtex
56
- @inproceedings{pylaia-lib,
57
- author = "Tarride, Solène and Schneider, Yoann and Generali, Marie and Boillet, Melodie and Abadie, Bastien and Kermorvant, Christopher",
58
- title = "Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library",
59
- booktitle = "Submitted at ICDAR2024",
60
- year = "2024"
 
 
 
 
61
  }
62
  ```
 
21
 
22
  # PyLaia - POPP
23
 
24
+ This model performs Handwritten Text Recognition in French on French census documents.
25
 
26
  ## Model description
27
 
28
  The model was trained using the PyLaia library on the [POPP generic](https://github.com/Shulk97/POPP-datasets/).
29
 
30
+ Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
31
 
32
+ | set | lines |
33
  | ----- | ------: |
34
  | train | 3,835 |
35
  | val | 480 |
 
41
 
42
  The model achieves the following results:
43
 
44
+ | set | Language model | CER (%) | WER (%) | lines |
45
+ |-------|:---------------| ----------:| -------:|--------:|
46
+ | test | no | 16.49 | 36.26 | 479 |
47
+ | test | yes | 16.09 | 34.52 479 |
48
 
49
  ## How to use?
50
 
51
+ Please refer to the [PyLaia documentation](https://atr.pages.teklia.com/pylaia/usage/prediction/) to use this model.
52
 
53
  ## Cite us!
54
 
55
  ```bibtex
56
+ @inproceedings{pylaia2024,
57
+ author = {Tarride, Solène and Schneider, Yoann and Generali-Lince, Marie and Boillet, Mélodie and Abadie, Bastien and Kermorvant, Christopher},
58
+ title = {{Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library}},
59
+ booktitle = {Document Analysis and Recognition - ICDAR 2024},
60
+ year = {2024},
61
+ publisher = {Springer Nature Switzerland},
62
+ address = {Cham},
63
+ pages = {387--404},
64
+ isbn = {978-3-031-70549-6}
65
  }
66
  ```